Presentation	1998/3/13 A new of model neural network searching for optimum solution Katuso Toguchi, Toshihiro Simizu,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	A new model of neural network is proposed:x_(t)=-μx_(t)+K(Σ^M_jΣ^N_lW_(t)+I_, y_(t)=(g_1tanh(βx_(t))+g_2)y_(t)-y_(t)^2, where x_(t)is the internal state and y_(t)is the output variable. This network is applied to the traveling salesman problem with 10 cities. This network can find the shortest path with the ratio of about 100%, even if the initial value of x_(t) and y_(t) are given at random. It is shown that the network can find the shortest path without being trapped in the local minima. The mechanism is investigated.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Neural network / Traveling salesman problem
Paper #
Date of Issue

Conference Information
Committee	NLP
Conference Date	1998/3/13(1days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To	Nonlinear Problems (NLP)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	A new of model neural network searching for optimum solution
Sub Title (in English)
Keyword(1)	Neural network
Keyword(2)	Traveling salesman problem
1st Author's Name	Katuso Toguchi
1st Author's Affiliation	Department of Electrical Engineering, Faculty of Engineering, Kokushikan University()
2nd Author's Name	Toshihiro Simizu
2nd Author's Affiliation	Department of Electrical Engineering, Faculty of Engineering, Kokushikan University
Date	1998/3/13
Paper #
Volume (vol)	vol.97
Number (no)	592
Page	pp.pp.-
#Pages	7
Date of Issue